A meta-analysis of the association between loneliness and all-cause mortality in older adults

Abstract

Despite the well-established association between loneliness and all-cause mortality in older adults, it remains unknown whether this association holds for older adults of different sex and whether it is influenced by different samples and study characteristics. Thus, this meta-analysis aims to examine moderators of the association between loneliness and all-cause mortality in older adults. To this end, relevant literature was retrieved from the PubMed, Embase, PsycINFO, Web of Science, Chinese National Knowledge Infrastructure, Weipu, and Wanfang databases (inception to May 2023) and was processed in the Comprehensive Meta-Analysis 3.3 software. Moreover, subgroup analysis was performed to explore the sources of heterogeneity and further explore potential moderators. Funnel plots, Begg's test, and Egger's linear regression test were used to examine the publication bias, and sensitivity analysis was used to test the robustness of the results. Thirty-six studies involving 128,927 older adults were included in this meta-analysis. In general, loneliness was related to an increase in all-cause mortality in older adults (HR = 1.09, 95% CI = 1.06-1.12, I² = 63.31%, p < 0.001). The overall effect size for older men was 1.18 (95% CI = 1.04-1.33, p = 0.010). The association between loneliness and all-cause mortality was found to be significantly influenced by the source country of the data, follow-up length, and covariates for chronic disease as moderators. In conclusion, loneliness among older adults deserves more attention, and services are needed to improve their mental health.

Keywords: All-cause mortality; Loneliness; Meta-analysis; Older adults.